Clustering the self-organizing map through the identification of core neuron regions

This paper presents an automatic clustering algorithm applied to SOM neurons. In the proposed method, every neuron has associated with it a weight and a feature vector, where the latter contains information of local density and local distances. The neurons are able to move in the SOM output grid so as to reach positions related to small pairwise distance among neurons and high density of patterns, but also taking into account the path cost to reach it. The positions to where the neurons converge are then used as benchmark for pruning the grid and revealing the core of the clusters. The method was evaluated through its application to synthetic and real world data sets.